{
  "best_metric": 0.5731000304222107,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.450070323488045,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011251758087201125,
      "grad_norm": 0.791208028793335,
      "learning_rate": 1e-05,
      "loss": 0.5861,
      "step": 1
    },
    {
      "epoch": 0.0011251758087201125,
      "eval_loss": 0.9892504811286926,
      "eval_runtime": 121.4392,
      "eval_samples_per_second": 12.327,
      "eval_steps_per_second": 3.088,
      "step": 1
    },
    {
      "epoch": 0.002250351617440225,
      "grad_norm": 0.7348774075508118,
      "learning_rate": 2e-05,
      "loss": 0.592,
      "step": 2
    },
    {
      "epoch": 0.0033755274261603376,
      "grad_norm": 0.741549015045166,
      "learning_rate": 3e-05,
      "loss": 0.6838,
      "step": 3
    },
    {
      "epoch": 0.00450070323488045,
      "grad_norm": 0.5738378167152405,
      "learning_rate": 4e-05,
      "loss": 0.7513,
      "step": 4
    },
    {
      "epoch": 0.005625879043600563,
      "grad_norm": 0.47346198558807373,
      "learning_rate": 5e-05,
      "loss": 0.8137,
      "step": 5
    },
    {
      "epoch": 0.006751054852320675,
      "grad_norm": 0.39620643854141235,
      "learning_rate": 6e-05,
      "loss": 0.733,
      "step": 6
    },
    {
      "epoch": 0.007876230661040788,
      "grad_norm": 0.9768288135528564,
      "learning_rate": 7e-05,
      "loss": 0.9303,
      "step": 7
    },
    {
      "epoch": 0.0090014064697609,
      "grad_norm": 0.7520477175712585,
      "learning_rate": 8e-05,
      "loss": 0.8512,
      "step": 8
    },
    {
      "epoch": 0.010126582278481013,
      "grad_norm": 0.4297806918621063,
      "learning_rate": 9e-05,
      "loss": 0.8734,
      "step": 9
    },
    {
      "epoch": 0.011251758087201125,
      "grad_norm": 0.4498920440673828,
      "learning_rate": 0.0001,
      "loss": 0.9123,
      "step": 10
    },
    {
      "epoch": 0.012376933895921238,
      "grad_norm": 0.5254006385803223,
      "learning_rate": 9.99983777858264e-05,
      "loss": 0.9156,
      "step": 11
    },
    {
      "epoch": 0.01350210970464135,
      "grad_norm": 0.4119812548160553,
      "learning_rate": 9.999351124856874e-05,
      "loss": 0.8029,
      "step": 12
    },
    {
      "epoch": 0.014627285513361463,
      "grad_norm": 0.34345316886901855,
      "learning_rate": 9.998540070400966e-05,
      "loss": 0.936,
      "step": 13
    },
    {
      "epoch": 0.015752461322081576,
      "grad_norm": 0.37706848978996277,
      "learning_rate": 9.997404667843075e-05,
      "loss": 0.9711,
      "step": 14
    },
    {
      "epoch": 0.016877637130801686,
      "grad_norm": 0.4172216057777405,
      "learning_rate": 9.995944990857849e-05,
      "loss": 0.8853,
      "step": 15
    },
    {
      "epoch": 0.0180028129395218,
      "grad_norm": 0.33668506145477295,
      "learning_rate": 9.994161134161634e-05,
      "loss": 0.9898,
      "step": 16
    },
    {
      "epoch": 0.01912798874824191,
      "grad_norm": 0.2785027027130127,
      "learning_rate": 9.992053213506334e-05,
      "loss": 0.8462,
      "step": 17
    },
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 0.3014741837978363,
      "learning_rate": 9.989621365671902e-05,
      "loss": 0.9212,
      "step": 18
    },
    {
      "epoch": 0.021378340365682136,
      "grad_norm": 0.3413006067276001,
      "learning_rate": 9.986865748457457e-05,
      "loss": 1.0007,
      "step": 19
    },
    {
      "epoch": 0.02250351617440225,
      "grad_norm": 0.29686427116394043,
      "learning_rate": 9.983786540671051e-05,
      "loss": 0.8971,
      "step": 20
    },
    {
      "epoch": 0.02362869198312236,
      "grad_norm": 0.30158573389053345,
      "learning_rate": 9.980383942118066e-05,
      "loss": 0.9584,
      "step": 21
    },
    {
      "epoch": 0.024753867791842476,
      "grad_norm": 0.2803223431110382,
      "learning_rate": 9.976658173588244e-05,
      "loss": 1.0235,
      "step": 22
    },
    {
      "epoch": 0.025879043600562587,
      "grad_norm": 0.2954846918582916,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.8306,
      "step": 23
    },
    {
      "epoch": 0.0270042194092827,
      "grad_norm": 0.29831573367118835,
      "learning_rate": 9.968238114591566e-05,
      "loss": 0.843,
      "step": 24
    },
    {
      "epoch": 0.02812939521800281,
      "grad_norm": 0.34613728523254395,
      "learning_rate": 9.96354437049027e-05,
      "loss": 0.7939,
      "step": 25
    },
    {
      "epoch": 0.029254571026722926,
      "grad_norm": 0.3171483874320984,
      "learning_rate": 9.95852854910781e-05,
      "loss": 0.7847,
      "step": 26
    },
    {
      "epoch": 0.030379746835443037,
      "grad_norm": 0.3092692494392395,
      "learning_rate": 9.953190975913647e-05,
      "loss": 0.9123,
      "step": 27
    },
    {
      "epoch": 0.03150492264416315,
      "grad_norm": 0.312860369682312,
      "learning_rate": 9.947531997255256e-05,
      "loss": 0.8217,
      "step": 28
    },
    {
      "epoch": 0.03263009845288326,
      "grad_norm": 0.34326767921447754,
      "learning_rate": 9.941551980335652e-05,
      "loss": 0.8803,
      "step": 29
    },
    {
      "epoch": 0.03375527426160337,
      "grad_norm": 0.3247174918651581,
      "learning_rate": 9.935251313189564e-05,
      "loss": 0.8407,
      "step": 30
    },
    {
      "epoch": 0.03488045007032349,
      "grad_norm": 0.31886929273605347,
      "learning_rate": 9.928630404658255e-05,
      "loss": 0.6957,
      "step": 31
    },
    {
      "epoch": 0.0360056258790436,
      "grad_norm": 0.30395761132240295,
      "learning_rate": 9.921689684362989e-05,
      "loss": 0.7102,
      "step": 32
    },
    {
      "epoch": 0.03713080168776371,
      "grad_norm": 0.32554319500923157,
      "learning_rate": 9.914429602677162e-05,
      "loss": 0.7969,
      "step": 33
    },
    {
      "epoch": 0.03825597749648382,
      "grad_norm": 0.335056871175766,
      "learning_rate": 9.906850630697068e-05,
      "loss": 0.6319,
      "step": 34
    },
    {
      "epoch": 0.03938115330520394,
      "grad_norm": 0.32416272163391113,
      "learning_rate": 9.898953260211338e-05,
      "loss": 0.6367,
      "step": 35
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 0.34065842628479004,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.7144,
      "step": 36
    },
    {
      "epoch": 0.04163150492264416,
      "grad_norm": 0.2950224280357361,
      "learning_rate": 9.882205394146361e-05,
      "loss": 0.5111,
      "step": 37
    },
    {
      "epoch": 0.04275668073136427,
      "grad_norm": 0.33300068974494934,
      "learning_rate": 9.87335598531214e-05,
      "loss": 0.5435,
      "step": 38
    },
    {
      "epoch": 0.04388185654008439,
      "grad_norm": 0.3185752034187317,
      "learning_rate": 9.864190351391822e-05,
      "loss": 0.4575,
      "step": 39
    },
    {
      "epoch": 0.0450070323488045,
      "grad_norm": 0.31263992190361023,
      "learning_rate": 9.85470908713026e-05,
      "loss": 0.5105,
      "step": 40
    },
    {
      "epoch": 0.04613220815752461,
      "grad_norm": 0.3303317129611969,
      "learning_rate": 9.844912807753104e-05,
      "loss": 0.5026,
      "step": 41
    },
    {
      "epoch": 0.04725738396624472,
      "grad_norm": 0.33453431725502014,
      "learning_rate": 9.834802148926882e-05,
      "loss": 0.4434,
      "step": 42
    },
    {
      "epoch": 0.04838255977496484,
      "grad_norm": 0.3641398251056671,
      "learning_rate": 9.824377766717759e-05,
      "loss": 0.5608,
      "step": 43
    },
    {
      "epoch": 0.04950773558368495,
      "grad_norm": 0.368456095457077,
      "learning_rate": 9.813640337548954e-05,
      "loss": 0.4456,
      "step": 44
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 0.38945502042770386,
      "learning_rate": 9.802590558156862e-05,
      "loss": 0.522,
      "step": 45
    },
    {
      "epoch": 0.05175808720112517,
      "grad_norm": 0.3877948224544525,
      "learning_rate": 9.791229145545831e-05,
      "loss": 0.3982,
      "step": 46
    },
    {
      "epoch": 0.05288326300984529,
      "grad_norm": 0.4522574245929718,
      "learning_rate": 9.779556836941645e-05,
      "loss": 0.3829,
      "step": 47
    },
    {
      "epoch": 0.0540084388185654,
      "grad_norm": 0.46986550092697144,
      "learning_rate": 9.767574389743682e-05,
      "loss": 0.4329,
      "step": 48
    },
    {
      "epoch": 0.05513361462728551,
      "grad_norm": 0.5505241751670837,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4547,
      "step": 49
    },
    {
      "epoch": 0.05625879043600562,
      "grad_norm": 0.6366212368011475,
      "learning_rate": 9.742682209735727e-05,
      "loss": 0.4432,
      "step": 50
    },
    {
      "epoch": 0.05625879043600562,
      "eval_loss": 0.6768447160720825,
      "eval_runtime": 122.3079,
      "eval_samples_per_second": 12.24,
      "eval_steps_per_second": 3.066,
      "step": 50
    },
    {
      "epoch": 0.05738396624472574,
      "grad_norm": 0.3021714985370636,
      "learning_rate": 9.729774092143627e-05,
      "loss": 0.4182,
      "step": 51
    },
    {
      "epoch": 0.05850914205344585,
      "grad_norm": 0.2832154929637909,
      "learning_rate": 9.716559066288715e-05,
      "loss": 0.4495,
      "step": 52
    },
    {
      "epoch": 0.05963431786216596,
      "grad_norm": 0.2705238461494446,
      "learning_rate": 9.703037989675087e-05,
      "loss": 0.546,
      "step": 53
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 0.24180416762828827,
      "learning_rate": 9.689211739666023e-05,
      "loss": 0.5842,
      "step": 54
    },
    {
      "epoch": 0.06188466947960619,
      "grad_norm": 0.22725558280944824,
      "learning_rate": 9.675081213427076e-05,
      "loss": 0.5901,
      "step": 55
    },
    {
      "epoch": 0.0630098452883263,
      "grad_norm": 0.2603343725204468,
      "learning_rate": 9.66064732786784e-05,
      "loss": 0.6602,
      "step": 56
    },
    {
      "epoch": 0.06413502109704641,
      "grad_norm": 0.2453056126832962,
      "learning_rate": 9.645911019582467e-05,
      "loss": 0.6428,
      "step": 57
    },
    {
      "epoch": 0.06526019690576652,
      "grad_norm": 0.2500747740268707,
      "learning_rate": 9.630873244788883e-05,
      "loss": 0.6843,
      "step": 58
    },
    {
      "epoch": 0.06638537271448663,
      "grad_norm": 0.23956970870494843,
      "learning_rate": 9.615534979266745e-05,
      "loss": 0.7583,
      "step": 59
    },
    {
      "epoch": 0.06751054852320675,
      "grad_norm": 0.23142866790294647,
      "learning_rate": 9.599897218294122e-05,
      "loss": 0.7374,
      "step": 60
    },
    {
      "epoch": 0.06863572433192687,
      "grad_norm": 0.2538938820362091,
      "learning_rate": 9.583960976582913e-05,
      "loss": 0.8349,
      "step": 61
    },
    {
      "epoch": 0.06976090014064698,
      "grad_norm": 0.24747668206691742,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7825,
      "step": 62
    },
    {
      "epoch": 0.07088607594936709,
      "grad_norm": 0.24818557500839233,
      "learning_rate": 9.551197206565173e-05,
      "loss": 0.7681,
      "step": 63
    },
    {
      "epoch": 0.0720112517580872,
      "grad_norm": 0.24176418781280518,
      "learning_rate": 9.534371804252728e-05,
      "loss": 0.7531,
      "step": 64
    },
    {
      "epoch": 0.07313642756680731,
      "grad_norm": 0.2653544843196869,
      "learning_rate": 9.517252173051911e-05,
      "loss": 0.912,
      "step": 65
    },
    {
      "epoch": 0.07426160337552742,
      "grad_norm": 0.2475324124097824,
      "learning_rate": 9.49983942383106e-05,
      "loss": 0.7183,
      "step": 66
    },
    {
      "epoch": 0.07538677918424753,
      "grad_norm": 0.25549477338790894,
      "learning_rate": 9.482134686478519e-05,
      "loss": 0.7015,
      "step": 67
    },
    {
      "epoch": 0.07651195499296765,
      "grad_norm": 0.2648347020149231,
      "learning_rate": 9.464139109829321e-05,
      "loss": 0.7304,
      "step": 68
    },
    {
      "epoch": 0.07763713080168777,
      "grad_norm": 0.2694757282733917,
      "learning_rate": 9.445853861590647e-05,
      "loss": 0.7315,
      "step": 69
    },
    {
      "epoch": 0.07876230661040788,
      "grad_norm": 0.2604469358921051,
      "learning_rate": 9.42728012826605e-05,
      "loss": 0.7452,
      "step": 70
    },
    {
      "epoch": 0.07988748241912799,
      "grad_norm": 0.2539106011390686,
      "learning_rate": 9.408419115078471e-05,
      "loss": 0.666,
      "step": 71
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 0.2885034680366516,
      "learning_rate": 9.389272045892024e-05,
      "loss": 0.9262,
      "step": 72
    },
    {
      "epoch": 0.08213783403656821,
      "grad_norm": 0.2839057743549347,
      "learning_rate": 9.36984016313259e-05,
      "loss": 0.7723,
      "step": 73
    },
    {
      "epoch": 0.08326300984528832,
      "grad_norm": 0.2611367702484131,
      "learning_rate": 9.350124727707197e-05,
      "loss": 0.6862,
      "step": 74
    },
    {
      "epoch": 0.08438818565400844,
      "grad_norm": 0.2865094542503357,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.8664,
      "step": 75
    },
    {
      "epoch": 0.08551336146272855,
      "grad_norm": 0.2991608679294586,
      "learning_rate": 9.309848334400246e-05,
      "loss": 0.8543,
      "step": 76
    },
    {
      "epoch": 0.08663853727144867,
      "grad_norm": 0.29869431257247925,
      "learning_rate": 9.289289989996133e-05,
      "loss": 0.7816,
      "step": 77
    },
    {
      "epoch": 0.08776371308016878,
      "grad_norm": 0.2918897867202759,
      "learning_rate": 9.268453319711363e-05,
      "loss": 0.7375,
      "step": 78
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.2945139706134796,
      "learning_rate": 9.247339675607605e-05,
      "loss": 0.797,
      "step": 79
    },
    {
      "epoch": 0.090014064697609,
      "grad_norm": 0.28907427191734314,
      "learning_rate": 9.225950427718975e-05,
      "loss": 0.6864,
      "step": 80
    },
    {
      "epoch": 0.09113924050632911,
      "grad_norm": 0.2843822240829468,
      "learning_rate": 9.204286963963111e-05,
      "loss": 0.6236,
      "step": 81
    },
    {
      "epoch": 0.09226441631504922,
      "grad_norm": 0.29010453820228577,
      "learning_rate": 9.182350690051133e-05,
      "loss": 0.6518,
      "step": 82
    },
    {
      "epoch": 0.09338959212376934,
      "grad_norm": 0.31116747856140137,
      "learning_rate": 9.160143029396422e-05,
      "loss": 0.6894,
      "step": 83
    },
    {
      "epoch": 0.09451476793248945,
      "grad_norm": 0.3072003424167633,
      "learning_rate": 9.13766542302225e-05,
      "loss": 0.6314,
      "step": 84
    },
    {
      "epoch": 0.09563994374120956,
      "grad_norm": 0.3316248953342438,
      "learning_rate": 9.114919329468282e-05,
      "loss": 0.6879,
      "step": 85
    },
    {
      "epoch": 0.09676511954992968,
      "grad_norm": 0.33323273062705994,
      "learning_rate": 9.091906224695935e-05,
      "loss": 0.6434,
      "step": 86
    },
    {
      "epoch": 0.09789029535864979,
      "grad_norm": 0.314699649810791,
      "learning_rate": 9.068627601992598e-05,
      "loss": 0.598,
      "step": 87
    },
    {
      "epoch": 0.0990154711673699,
      "grad_norm": 0.3086985647678375,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5176,
      "step": 88
    },
    {
      "epoch": 0.10014064697609001,
      "grad_norm": 0.31014567613601685,
      "learning_rate": 9.021279861989885e-05,
      "loss": 0.5924,
      "step": 89
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 0.3152261972427368,
      "learning_rate": 8.997213817017507e-05,
      "loss": 0.459,
      "step": 90
    },
    {
      "epoch": 0.10239099859353024,
      "grad_norm": 0.31608080863952637,
      "learning_rate": 8.972888398568772e-05,
      "loss": 0.4356,
      "step": 91
    },
    {
      "epoch": 0.10351617440225035,
      "grad_norm": 0.312263548374176,
      "learning_rate": 8.948305185085225e-05,
      "loss": 0.3729,
      "step": 92
    },
    {
      "epoch": 0.10464135021097046,
      "grad_norm": 0.3479161858558655,
      "learning_rate": 8.92346577173636e-05,
      "loss": 0.4006,
      "step": 93
    },
    {
      "epoch": 0.10576652601969058,
      "grad_norm": 0.3391091823577881,
      "learning_rate": 8.898371770316111e-05,
      "loss": 0.4098,
      "step": 94
    },
    {
      "epoch": 0.10689170182841069,
      "grad_norm": 0.37615877389907837,
      "learning_rate": 8.873024809138272e-05,
      "loss": 0.3537,
      "step": 95
    },
    {
      "epoch": 0.1080168776371308,
      "grad_norm": 0.38181978464126587,
      "learning_rate": 8.847426532930831e-05,
      "loss": 0.4301,
      "step": 96
    },
    {
      "epoch": 0.10914205344585091,
      "grad_norm": 0.398378849029541,
      "learning_rate": 8.821578602729242e-05,
      "loss": 0.4368,
      "step": 97
    },
    {
      "epoch": 0.11026722925457103,
      "grad_norm": 0.4197014272212982,
      "learning_rate": 8.795482695768658e-05,
      "loss": 0.4488,
      "step": 98
    },
    {
      "epoch": 0.11139240506329114,
      "grad_norm": 0.4649895429611206,
      "learning_rate": 8.769140505375085e-05,
      "loss": 0.4162,
      "step": 99
    },
    {
      "epoch": 0.11251758087201125,
      "grad_norm": 0.6387284398078918,
      "learning_rate": 8.742553740855506e-05,
      "loss": 0.4822,
      "step": 100
    },
    {
      "epoch": 0.11251758087201125,
      "eval_loss": 0.644762396812439,
      "eval_runtime": 122.8498,
      "eval_samples_per_second": 12.186,
      "eval_steps_per_second": 3.053,
      "step": 100
    },
    {
      "epoch": 0.11364275668073136,
      "grad_norm": 0.28204846382141113,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.4037,
      "step": 101
    },
    {
      "epoch": 0.11476793248945148,
      "grad_norm": 0.2628364562988281,
      "learning_rate": 8.688653405904652e-05,
      "loss": 0.4282,
      "step": 102
    },
    {
      "epoch": 0.1158931082981716,
      "grad_norm": 0.24635303020477295,
      "learning_rate": 8.661343332988869e-05,
      "loss": 0.4933,
      "step": 103
    },
    {
      "epoch": 0.1170182841068917,
      "grad_norm": 0.22415153682231903,
      "learning_rate": 8.633795680751116e-05,
      "loss": 0.5442,
      "step": 104
    },
    {
      "epoch": 0.11814345991561181,
      "grad_norm": 0.2219788134098053,
      "learning_rate": 8.606012236719073e-05,
      "loss": 0.6066,
      "step": 105
    },
    {
      "epoch": 0.11926863572433193,
      "grad_norm": 0.2294948548078537,
      "learning_rate": 8.577994803720606e-05,
      "loss": 0.6212,
      "step": 106
    },
    {
      "epoch": 0.12039381153305204,
      "grad_norm": 0.23675329983234406,
      "learning_rate": 8.549745199766792e-05,
      "loss": 0.6921,
      "step": 107
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 0.24186259508132935,
      "learning_rate": 8.521265257933948e-05,
      "loss": 0.6363,
      "step": 108
    },
    {
      "epoch": 0.12264416315049226,
      "grad_norm": 0.23978343605995178,
      "learning_rate": 8.492556826244687e-05,
      "loss": 0.7421,
      "step": 109
    },
    {
      "epoch": 0.12376933895921238,
      "grad_norm": 0.22931262850761414,
      "learning_rate": 8.463621767547998e-05,
      "loss": 0.6781,
      "step": 110
    },
    {
      "epoch": 0.1248945147679325,
      "grad_norm": 0.2452748417854309,
      "learning_rate": 8.434461959398376e-05,
      "loss": 0.7911,
      "step": 111
    },
    {
      "epoch": 0.1260196905766526,
      "grad_norm": 0.25769487023353577,
      "learning_rate": 8.405079293933986e-05,
      "loss": 0.8928,
      "step": 112
    },
    {
      "epoch": 0.1271448663853727,
      "grad_norm": 0.26870453357696533,
      "learning_rate": 8.375475677753881e-05,
      "loss": 0.8826,
      "step": 113
    },
    {
      "epoch": 0.12827004219409283,
      "grad_norm": 0.2632165253162384,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.85,
      "step": 114
    },
    {
      "epoch": 0.12939521800281295,
      "grad_norm": 0.2665436267852783,
      "learning_rate": 8.315613291203976e-05,
      "loss": 0.9165,
      "step": 115
    },
    {
      "epoch": 0.13052039381153305,
      "grad_norm": 0.25475484132766724,
      "learning_rate": 8.285358405218655e-05,
      "loss": 0.7661,
      "step": 116
    },
    {
      "epoch": 0.13164556962025317,
      "grad_norm": 0.2527354657649994,
      "learning_rate": 8.25489033703452e-05,
      "loss": 0.7149,
      "step": 117
    },
    {
      "epoch": 0.13277074542897327,
      "grad_norm": 0.25752562284469604,
      "learning_rate": 8.224211063680853e-05,
      "loss": 0.8108,
      "step": 118
    },
    {
      "epoch": 0.1338959212376934,
      "grad_norm": 0.25537046790122986,
      "learning_rate": 8.19332257589174e-05,
      "loss": 0.6797,
      "step": 119
    },
    {
      "epoch": 0.1350210970464135,
      "grad_norm": 0.2648957371711731,
      "learning_rate": 8.162226877976887e-05,
      "loss": 0.7278,
      "step": 120
    },
    {
      "epoch": 0.13614627285513362,
      "grad_norm": 0.27850714325904846,
      "learning_rate": 8.130925987691569e-05,
      "loss": 0.718,
      "step": 121
    },
    {
      "epoch": 0.13727144866385374,
      "grad_norm": 0.2784062623977661,
      "learning_rate": 8.099421936105702e-05,
      "loss": 0.7789,
      "step": 122
    },
    {
      "epoch": 0.13839662447257384,
      "grad_norm": 0.2852023243904114,
      "learning_rate": 8.067716767472045e-05,
      "loss": 0.7814,
      "step": 123
    },
    {
      "epoch": 0.13952180028129396,
      "grad_norm": 0.3003855347633362,
      "learning_rate": 8.035812539093557e-05,
      "loss": 0.8263,
      "step": 124
    },
    {
      "epoch": 0.14064697609001406,
      "grad_norm": 0.2815362215042114,
      "learning_rate": 8.003711321189895e-05,
      "loss": 0.7245,
      "step": 125
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 0.2952372133731842,
      "learning_rate": 7.971415196763088e-05,
      "loss": 0.8003,
      "step": 126
    },
    {
      "epoch": 0.14289732770745428,
      "grad_norm": 0.30167871713638306,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7914,
      "step": 127
    },
    {
      "epoch": 0.1440225035161744,
      "grad_norm": 0.30462878942489624,
      "learning_rate": 7.906246623448183e-05,
      "loss": 0.8007,
      "step": 128
    },
    {
      "epoch": 0.1451476793248945,
      "grad_norm": 0.3005084991455078,
      "learning_rate": 7.873378403255419e-05,
      "loss": 0.7998,
      "step": 129
    },
    {
      "epoch": 0.14627285513361463,
      "grad_norm": 0.30115005373954773,
      "learning_rate": 7.840323733655778e-05,
      "loss": 0.7084,
      "step": 130
    },
    {
      "epoch": 0.14739803094233475,
      "grad_norm": 0.29491057991981506,
      "learning_rate": 7.807084759519405e-05,
      "loss": 0.6415,
      "step": 131
    },
    {
      "epoch": 0.14852320675105485,
      "grad_norm": 0.30844321846961975,
      "learning_rate": 7.773663637675694e-05,
      "loss": 0.7082,
      "step": 132
    },
    {
      "epoch": 0.14964838255977497,
      "grad_norm": 0.30617377161979675,
      "learning_rate": 7.740062536773352e-05,
      "loss": 0.658,
      "step": 133
    },
    {
      "epoch": 0.15077355836849507,
      "grad_norm": 0.3148016929626465,
      "learning_rate": 7.706283637139658e-05,
      "loss": 0.6561,
      "step": 134
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 0.31739330291748047,
      "learning_rate": 7.672329130639005e-05,
      "loss": 0.6966,
      "step": 135
    },
    {
      "epoch": 0.1530239099859353,
      "grad_norm": 0.30230337381362915,
      "learning_rate": 7.638201220530665e-05,
      "loss": 0.482,
      "step": 136
    },
    {
      "epoch": 0.15414908579465542,
      "grad_norm": 0.3207411766052246,
      "learning_rate": 7.603902121325813e-05,
      "loss": 0.6072,
      "step": 137
    },
    {
      "epoch": 0.15527426160337554,
      "grad_norm": 0.3160305917263031,
      "learning_rate": 7.569434058643844e-05,
      "loss": 0.5652,
      "step": 138
    },
    {
      "epoch": 0.15639943741209564,
      "grad_norm": 0.30304470658302307,
      "learning_rate": 7.534799269067953e-05,
      "loss": 0.4681,
      "step": 139
    },
    {
      "epoch": 0.15752461322081576,
      "grad_norm": 0.3202410042285919,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4403,
      "step": 140
    },
    {
      "epoch": 0.15864978902953586,
      "grad_norm": 0.32677364349365234,
      "learning_rate": 7.465038509514688e-05,
      "loss": 0.4632,
      "step": 141
    },
    {
      "epoch": 0.15977496483825598,
      "grad_norm": 0.35057735443115234,
      "learning_rate": 7.42991706621303e-05,
      "loss": 0.5051,
      "step": 142
    },
    {
      "epoch": 0.16090014064697608,
      "grad_norm": 0.34558597207069397,
      "learning_rate": 7.394637949075154e-05,
      "loss": 0.4052,
      "step": 143
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 0.35772836208343506,
      "learning_rate": 7.35920344731241e-05,
      "loss": 0.407,
      "step": 144
    },
    {
      "epoch": 0.1631504922644163,
      "grad_norm": 0.3630152642726898,
      "learning_rate": 7.323615860218843e-05,
      "loss": 0.4163,
      "step": 145
    },
    {
      "epoch": 0.16427566807313643,
      "grad_norm": 0.3928242325782776,
      "learning_rate": 7.287877497021978e-05,
      "loss": 0.4362,
      "step": 146
    },
    {
      "epoch": 0.16540084388185655,
      "grad_norm": 0.45405474305152893,
      "learning_rate": 7.251990676732984e-05,
      "loss": 0.5051,
      "step": 147
    },
    {
      "epoch": 0.16652601969057665,
      "grad_norm": 0.4049229323863983,
      "learning_rate": 7.215957727996207e-05,
      "loss": 0.353,
      "step": 148
    },
    {
      "epoch": 0.16765119549929677,
      "grad_norm": 0.49053892493247986,
      "learning_rate": 7.179780988938051e-05,
      "loss": 0.358,
      "step": 149
    },
    {
      "epoch": 0.16877637130801687,
      "grad_norm": 0.6350364685058594,
      "learning_rate": 7.143462807015271e-05,
      "loss": 0.4267,
      "step": 150
    },
    {
      "epoch": 0.16877637130801687,
      "eval_loss": 0.6191428303718567,
      "eval_runtime": 122.8049,
      "eval_samples_per_second": 12.19,
      "eval_steps_per_second": 3.054,
      "step": 150
    },
    {
      "epoch": 0.169901547116737,
      "grad_norm": 0.22611109912395477,
      "learning_rate": 7.107005538862646e-05,
      "loss": 0.3608,
      "step": 151
    },
    {
      "epoch": 0.1710267229254571,
      "grad_norm": 0.2486761510372162,
      "learning_rate": 7.07041155014006e-05,
      "loss": 0.4149,
      "step": 152
    },
    {
      "epoch": 0.17215189873417722,
      "grad_norm": 0.22183437645435333,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.4472,
      "step": 153
    },
    {
      "epoch": 0.17327707454289734,
      "grad_norm": 0.24657611548900604,
      "learning_rate": 6.996822917828477e-05,
      "loss": 0.5571,
      "step": 154
    },
    {
      "epoch": 0.17440225035161744,
      "grad_norm": 0.22693145275115967,
      "learning_rate": 6.959833049300377e-05,
      "loss": 0.5807,
      "step": 155
    },
    {
      "epoch": 0.17552742616033756,
      "grad_norm": 0.22520385682582855,
      "learning_rate": 6.922716010014255e-05,
      "loss": 0.5593,
      "step": 156
    },
    {
      "epoch": 0.17665260196905766,
      "grad_norm": 0.24080556631088257,
      "learning_rate": 6.885474208441603e-05,
      "loss": 0.6988,
      "step": 157
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.23336027562618256,
      "learning_rate": 6.848110061149556e-05,
      "loss": 0.6938,
      "step": 158
    },
    {
      "epoch": 0.17890295358649788,
      "grad_norm": 0.24269425868988037,
      "learning_rate": 6.810625992644085e-05,
      "loss": 0.6492,
      "step": 159
    },
    {
      "epoch": 0.180028129395218,
      "grad_norm": 0.257687509059906,
      "learning_rate": 6.773024435212678e-05,
      "loss": 0.7288,
      "step": 160
    },
    {
      "epoch": 0.1811533052039381,
      "grad_norm": 0.24201682209968567,
      "learning_rate": 6.735307828766515e-05,
      "loss": 0.7097,
      "step": 161
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 0.2506401538848877,
      "learning_rate": 6.697478620682137e-05,
      "loss": 0.7142,
      "step": 162
    },
    {
      "epoch": 0.18340365682137835,
      "grad_norm": 0.2325735092163086,
      "learning_rate": 6.659539265642643e-05,
      "loss": 0.6644,
      "step": 163
    },
    {
      "epoch": 0.18452883263009845,
      "grad_norm": 0.2502652704715729,
      "learning_rate": 6.621492225478414e-05,
      "loss": 0.7367,
      "step": 164
    },
    {
      "epoch": 0.18565400843881857,
      "grad_norm": 0.2414039522409439,
      "learning_rate": 6.583339969007363e-05,
      "loss": 0.7728,
      "step": 165
    },
    {
      "epoch": 0.18677918424753867,
      "grad_norm": 0.2699027359485626,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8384,
      "step": 166
    },
    {
      "epoch": 0.1879043600562588,
      "grad_norm": 0.2658804655075073,
      "learning_rate": 6.506729716392481e-05,
      "loss": 0.8469,
      "step": 167
    },
    {
      "epoch": 0.1890295358649789,
      "grad_norm": 0.25071781873703003,
      "learning_rate": 6.468276691378155e-05,
      "loss": 0.6885,
      "step": 168
    },
    {
      "epoch": 0.19015471167369902,
      "grad_norm": 0.2700413763523102,
      "learning_rate": 6.429728391993446e-05,
      "loss": 0.825,
      "step": 169
    },
    {
      "epoch": 0.19127988748241911,
      "grad_norm": 0.27662935853004456,
      "learning_rate": 6.391087319582264e-05,
      "loss": 0.8351,
      "step": 170
    },
    {
      "epoch": 0.19240506329113924,
      "grad_norm": 0.26488763093948364,
      "learning_rate": 6.35235598150842e-05,
      "loss": 0.7827,
      "step": 171
    },
    {
      "epoch": 0.19353023909985936,
      "grad_norm": 0.2654742896556854,
      "learning_rate": 6.313536890992935e-05,
      "loss": 0.8177,
      "step": 172
    },
    {
      "epoch": 0.19465541490857946,
      "grad_norm": 0.2809375822544098,
      "learning_rate": 6.274632566950967e-05,
      "loss": 0.8218,
      "step": 173
    },
    {
      "epoch": 0.19578059071729959,
      "grad_norm": 0.26899024844169617,
      "learning_rate": 6.235645533828349e-05,
      "loss": 0.7878,
      "step": 174
    },
    {
      "epoch": 0.19690576652601968,
      "grad_norm": 0.2818717062473297,
      "learning_rate": 6.19657832143779e-05,
      "loss": 0.785,
      "step": 175
    },
    {
      "epoch": 0.1980309423347398,
      "grad_norm": 0.3077673316001892,
      "learning_rate": 6.157433464794716e-05,
      "loss": 0.8369,
      "step": 176
    },
    {
      "epoch": 0.1991561181434599,
      "grad_norm": 0.277925580739975,
      "learning_rate": 6.118213503952779e-05,
      "loss": 0.6012,
      "step": 177
    },
    {
      "epoch": 0.20028129395218003,
      "grad_norm": 0.28356897830963135,
      "learning_rate": 6.078920983839031e-05,
      "loss": 0.7352,
      "step": 178
    },
    {
      "epoch": 0.20140646976090015,
      "grad_norm": 0.2859312891960144,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.719,
      "step": 179
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 0.31765639781951904,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 0.8586,
      "step": 180
    },
    {
      "epoch": 0.20365682137834037,
      "grad_norm": 0.2968887984752655,
      "learning_rate": 5.960633586768543e-05,
      "loss": 0.6802,
      "step": 181
    },
    {
      "epoch": 0.20478199718706047,
      "grad_norm": 0.294272780418396,
      "learning_rate": 5.921076370520058e-05,
      "loss": 0.6895,
      "step": 182
    },
    {
      "epoch": 0.2059071729957806,
      "grad_norm": 0.3082694709300995,
      "learning_rate": 5.8814593869458455e-05,
      "loss": 0.7071,
      "step": 183
    },
    {
      "epoch": 0.2070323488045007,
      "grad_norm": 0.3072359561920166,
      "learning_rate": 5.841785206735192e-05,
      "loss": 0.6542,
      "step": 184
    },
    {
      "epoch": 0.20815752461322082,
      "grad_norm": 0.28556135296821594,
      "learning_rate": 5.8020564042888015e-05,
      "loss": 0.5641,
      "step": 185
    },
    {
      "epoch": 0.20928270042194091,
      "grad_norm": 0.3505888283252716,
      "learning_rate": 5.762275557551727e-05,
      "loss": 0.8211,
      "step": 186
    },
    {
      "epoch": 0.21040787623066104,
      "grad_norm": 0.3167312443256378,
      "learning_rate": 5.7224452478461064e-05,
      "loss": 0.5715,
      "step": 187
    },
    {
      "epoch": 0.21153305203938116,
      "grad_norm": 0.30357834696769714,
      "learning_rate": 5.682568059703659e-05,
      "loss": 0.5422,
      "step": 188
    },
    {
      "epoch": 0.21265822784810126,
      "grad_norm": 0.28745442628860474,
      "learning_rate": 5.642646580697973e-05,
      "loss": 0.3673,
      "step": 189
    },
    {
      "epoch": 0.21378340365682139,
      "grad_norm": 0.32116490602493286,
      "learning_rate": 5.602683401276615e-05,
      "loss": 0.4719,
      "step": 190
    },
    {
      "epoch": 0.21490857946554148,
      "grad_norm": 0.31803691387176514,
      "learning_rate": 5.562681114593028e-05,
      "loss": 0.4755,
      "step": 191
    },
    {
      "epoch": 0.2160337552742616,
      "grad_norm": 0.3275885283946991,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.4121,
      "step": 192
    },
    {
      "epoch": 0.2171589310829817,
      "grad_norm": 0.3217777907848358,
      "learning_rate": 5.482569604572576e-05,
      "loss": 0.3525,
      "step": 193
    },
    {
      "epoch": 0.21828410689170183,
      "grad_norm": 0.33562275767326355,
      "learning_rate": 5.442465579556793e-05,
      "loss": 0.3489,
      "step": 194
    },
    {
      "epoch": 0.21940928270042195,
      "grad_norm": 0.3709050416946411,
      "learning_rate": 5.402332843583631e-05,
      "loss": 0.4602,
      "step": 195
    },
    {
      "epoch": 0.22053445850914205,
      "grad_norm": 0.3461264371871948,
      "learning_rate": 5.3621740008088126e-05,
      "loss": 0.3244,
      "step": 196
    },
    {
      "epoch": 0.22165963431786218,
      "grad_norm": 0.40534359216690063,
      "learning_rate": 5.321991657082097e-05,
      "loss": 0.4012,
      "step": 197
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 0.425788015127182,
      "learning_rate": 5.281788419778187e-05,
      "loss": 0.3741,
      "step": 198
    },
    {
      "epoch": 0.2239099859353024,
      "grad_norm": 0.47200363874435425,
      "learning_rate": 5.2415668976275355e-05,
      "loss": 0.3717,
      "step": 199
    },
    {
      "epoch": 0.2250351617440225,
      "grad_norm": 0.5842266082763672,
      "learning_rate": 5.201329700547076e-05,
      "loss": 0.4174,
      "step": 200
    },
    {
      "epoch": 0.2250351617440225,
      "eval_loss": 0.6018708348274231,
      "eval_runtime": 122.7147,
      "eval_samples_per_second": 12.199,
      "eval_steps_per_second": 3.056,
      "step": 200
    },
    {
      "epoch": 0.22616033755274262,
      "grad_norm": 0.19296161830425262,
      "learning_rate": 5.161079439470866e-05,
      "loss": 0.3172,
      "step": 201
    },
    {
      "epoch": 0.22728551336146272,
      "grad_norm": 0.2037908434867859,
      "learning_rate": 5.1208187261806615e-05,
      "loss": 0.4096,
      "step": 202
    },
    {
      "epoch": 0.22841068917018284,
      "grad_norm": 0.23043642938137054,
      "learning_rate": 5.080550173136457e-05,
      "loss": 0.4616,
      "step": 203
    },
    {
      "epoch": 0.22953586497890296,
      "grad_norm": 0.24173596501350403,
      "learning_rate": 5.0402763933069496e-05,
      "loss": 0.5913,
      "step": 204
    },
    {
      "epoch": 0.23066104078762306,
      "grad_norm": 0.22251668572425842,
      "learning_rate": 5e-05,
      "loss": 0.5383,
      "step": 205
    },
    {
      "epoch": 0.2317862165963432,
      "grad_norm": 0.23674923181533813,
      "learning_rate": 4.9597236066930516e-05,
      "loss": 0.6536,
      "step": 206
    },
    {
      "epoch": 0.23291139240506328,
      "grad_norm": 0.22485093772411346,
      "learning_rate": 4.919449826863544e-05,
      "loss": 0.5736,
      "step": 207
    },
    {
      "epoch": 0.2340365682137834,
      "grad_norm": 0.23937222361564636,
      "learning_rate": 4.87918127381934e-05,
      "loss": 0.7585,
      "step": 208
    },
    {
      "epoch": 0.2351617440225035,
      "grad_norm": 0.23238810896873474,
      "learning_rate": 4.8389205605291365e-05,
      "loss": 0.647,
      "step": 209
    },
    {
      "epoch": 0.23628691983122363,
      "grad_norm": 0.24751240015029907,
      "learning_rate": 4.798670299452926e-05,
      "loss": 0.7593,
      "step": 210
    },
    {
      "epoch": 0.23741209563994375,
      "grad_norm": 0.24134927988052368,
      "learning_rate": 4.758433102372466e-05,
      "loss": 0.6838,
      "step": 211
    },
    {
      "epoch": 0.23853727144866385,
      "grad_norm": 0.2430945336818695,
      "learning_rate": 4.7182115802218126e-05,
      "loss": 0.6795,
      "step": 212
    },
    {
      "epoch": 0.23966244725738398,
      "grad_norm": 0.24926406145095825,
      "learning_rate": 4.678008342917903e-05,
      "loss": 0.6832,
      "step": 213
    },
    {
      "epoch": 0.24078762306610407,
      "grad_norm": 0.27010077238082886,
      "learning_rate": 4.6378259991911886e-05,
      "loss": 0.8451,
      "step": 214
    },
    {
      "epoch": 0.2419127988748242,
      "grad_norm": 0.25659826397895813,
      "learning_rate": 4.597667156416371e-05,
      "loss": 0.8018,
      "step": 215
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 0.26555147767066956,
      "learning_rate": 4.5575344204432084e-05,
      "loss": 0.8489,
      "step": 216
    },
    {
      "epoch": 0.24416315049226442,
      "grad_norm": 0.26006457209587097,
      "learning_rate": 4.5174303954274244e-05,
      "loss": 0.7798,
      "step": 217
    },
    {
      "epoch": 0.24528832630098452,
      "grad_norm": 0.2641880214214325,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7372,
      "step": 218
    },
    {
      "epoch": 0.24641350210970464,
      "grad_norm": 0.2819690406322479,
      "learning_rate": 4.437318885406973e-05,
      "loss": 0.9184,
      "step": 219
    },
    {
      "epoch": 0.24753867791842477,
      "grad_norm": 0.26662251353263855,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.788,
      "step": 220
    },
    {
      "epoch": 0.24866385372714486,
      "grad_norm": 0.2747672200202942,
      "learning_rate": 4.3573534193020274e-05,
      "loss": 0.7521,
      "step": 221
    },
    {
      "epoch": 0.249789029535865,
      "grad_norm": 0.2652323842048645,
      "learning_rate": 4.317431940296343e-05,
      "loss": 0.7034,
      "step": 222
    },
    {
      "epoch": 0.2509142053445851,
      "grad_norm": 0.2707549035549164,
      "learning_rate": 4.277554752153895e-05,
      "loss": 0.7233,
      "step": 223
    },
    {
      "epoch": 0.2520393811533052,
      "grad_norm": 0.25702497363090515,
      "learning_rate": 4.237724442448273e-05,
      "loss": 0.637,
      "step": 224
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.2797415852546692,
      "learning_rate": 4.197943595711198e-05,
      "loss": 0.7079,
      "step": 225
    },
    {
      "epoch": 0.2542897327707454,
      "grad_norm": 0.26651498675346375,
      "learning_rate": 4.1582147932648074e-05,
      "loss": 0.7022,
      "step": 226
    },
    {
      "epoch": 0.2554149085794655,
      "grad_norm": 0.28537195920944214,
      "learning_rate": 4.118540613054156e-05,
      "loss": 0.7823,
      "step": 227
    },
    {
      "epoch": 0.25654008438818565,
      "grad_norm": 0.301383912563324,
      "learning_rate": 4.078923629479943e-05,
      "loss": 0.7906,
      "step": 228
    },
    {
      "epoch": 0.2576652601969058,
      "grad_norm": 0.3013364374637604,
      "learning_rate": 4.039366413231458e-05,
      "loss": 0.7727,
      "step": 229
    },
    {
      "epoch": 0.2587904360056259,
      "grad_norm": 0.2738421857357025,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 0.6249,
      "step": 230
    },
    {
      "epoch": 0.25991561181434597,
      "grad_norm": 0.31420156359672546,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.8525,
      "step": 231
    },
    {
      "epoch": 0.2610407876230661,
      "grad_norm": 0.28208857774734497,
      "learning_rate": 3.92107901616097e-05,
      "loss": 0.6143,
      "step": 232
    },
    {
      "epoch": 0.2621659634317862,
      "grad_norm": 0.29040223360061646,
      "learning_rate": 3.8817864960472236e-05,
      "loss": 0.6351,
      "step": 233
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 0.3167511224746704,
      "learning_rate": 3.842566535205286e-05,
      "loss": 0.5947,
      "step": 234
    },
    {
      "epoch": 0.26441631504922647,
      "grad_norm": 0.30433058738708496,
      "learning_rate": 3.803421678562213e-05,
      "loss": 0.5977,
      "step": 235
    },
    {
      "epoch": 0.26554149085794654,
      "grad_norm": 0.2989290952682495,
      "learning_rate": 3.764354466171652e-05,
      "loss": 0.5009,
      "step": 236
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.3097265064716339,
      "learning_rate": 3.725367433049033e-05,
      "loss": 0.5652,
      "step": 237
    },
    {
      "epoch": 0.2677918424753868,
      "grad_norm": 0.31169530749320984,
      "learning_rate": 3.6864631090070655e-05,
      "loss": 0.5104,
      "step": 238
    },
    {
      "epoch": 0.2689170182841069,
      "grad_norm": 0.3056240379810333,
      "learning_rate": 3.6476440184915815e-05,
      "loss": 0.4947,
      "step": 239
    },
    {
      "epoch": 0.270042194092827,
      "grad_norm": 0.3068471848964691,
      "learning_rate": 3.608912680417737e-05,
      "loss": 0.4709,
      "step": 240
    },
    {
      "epoch": 0.2711673699015471,
      "grad_norm": 0.3218245804309845,
      "learning_rate": 3.570271608006555e-05,
      "loss": 0.4978,
      "step": 241
    },
    {
      "epoch": 0.27229254571026723,
      "grad_norm": 0.2946934700012207,
      "learning_rate": 3.531723308621847e-05,
      "loss": 0.3584,
      "step": 242
    },
    {
      "epoch": 0.27341772151898736,
      "grad_norm": 0.3193693161010742,
      "learning_rate": 3.493270283607522e-05,
      "loss": 0.4092,
      "step": 243
    },
    {
      "epoch": 0.2745428973277075,
      "grad_norm": 0.32379648089408875,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3391,
      "step": 244
    },
    {
      "epoch": 0.27566807313642755,
      "grad_norm": 0.36625102162361145,
      "learning_rate": 3.4166600309926387e-05,
      "loss": 0.417,
      "step": 245
    },
    {
      "epoch": 0.2767932489451477,
      "grad_norm": 0.3967529237270355,
      "learning_rate": 3.3785077745215873e-05,
      "loss": 0.4547,
      "step": 246
    },
    {
      "epoch": 0.2779184247538678,
      "grad_norm": 0.4104136824607849,
      "learning_rate": 3.340460734357359e-05,
      "loss": 0.4187,
      "step": 247
    },
    {
      "epoch": 0.2790436005625879,
      "grad_norm": 0.4106130301952362,
      "learning_rate": 3.3025213793178646e-05,
      "loss": 0.3858,
      "step": 248
    },
    {
      "epoch": 0.280168776371308,
      "grad_norm": 0.45233193039894104,
      "learning_rate": 3.264692171233485e-05,
      "loss": 0.352,
      "step": 249
    },
    {
      "epoch": 0.2812939521800281,
      "grad_norm": 0.47355005145072937,
      "learning_rate": 3.226975564787322e-05,
      "loss": 0.295,
      "step": 250
    },
    {
      "epoch": 0.2812939521800281,
      "eval_loss": 0.5867157578468323,
      "eval_runtime": 122.2413,
      "eval_samples_per_second": 12.246,
      "eval_steps_per_second": 3.068,
      "step": 250
    },
    {
      "epoch": 0.28241912798874824,
      "grad_norm": 0.211994931101799,
      "learning_rate": 3.189374007355917e-05,
      "loss": 0.4111,
      "step": 251
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 0.20463378727436066,
      "learning_rate": 3.151889938850445e-05,
      "loss": 0.382,
      "step": 252
    },
    {
      "epoch": 0.2846694796061885,
      "grad_norm": 0.1885218471288681,
      "learning_rate": 3.114525791558398e-05,
      "loss": 0.386,
      "step": 253
    },
    {
      "epoch": 0.28579465541490856,
      "grad_norm": 0.2250271886587143,
      "learning_rate": 3.0772839899857464e-05,
      "loss": 0.5242,
      "step": 254
    },
    {
      "epoch": 0.2869198312236287,
      "grad_norm": 0.22449398040771484,
      "learning_rate": 3.0401669506996256e-05,
      "loss": 0.4741,
      "step": 255
    },
    {
      "epoch": 0.2880450070323488,
      "grad_norm": 0.22009386122226715,
      "learning_rate": 3.003177082171523e-05,
      "loss": 0.5467,
      "step": 256
    },
    {
      "epoch": 0.28917018284106893,
      "grad_norm": 0.2301923781633377,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.6133,
      "step": 257
    },
    {
      "epoch": 0.290295358649789,
      "grad_norm": 0.22307683527469635,
      "learning_rate": 2.9295884498599414e-05,
      "loss": 0.5158,
      "step": 258
    },
    {
      "epoch": 0.29142053445850913,
      "grad_norm": 0.25228241086006165,
      "learning_rate": 2.8929944611373554e-05,
      "loss": 0.788,
      "step": 259
    },
    {
      "epoch": 0.29254571026722925,
      "grad_norm": 0.23485252261161804,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 0.6315,
      "step": 260
    },
    {
      "epoch": 0.2936708860759494,
      "grad_norm": 0.24391689896583557,
      "learning_rate": 2.8202190110619493e-05,
      "loss": 0.7767,
      "step": 261
    },
    {
      "epoch": 0.2947960618846695,
      "grad_norm": 0.24884432554244995,
      "learning_rate": 2.784042272003794e-05,
      "loss": 0.7886,
      "step": 262
    },
    {
      "epoch": 0.29592123769338957,
      "grad_norm": 0.2370489090681076,
      "learning_rate": 2.7480093232670158e-05,
      "loss": 0.7015,
      "step": 263
    },
    {
      "epoch": 0.2970464135021097,
      "grad_norm": 0.25279098749160767,
      "learning_rate": 2.712122502978024e-05,
      "loss": 0.8111,
      "step": 264
    },
    {
      "epoch": 0.2981715893108298,
      "grad_norm": 0.24870732426643372,
      "learning_rate": 2.6763841397811573e-05,
      "loss": 0.7925,
      "step": 265
    },
    {
      "epoch": 0.29929676511954995,
      "grad_norm": 0.2534269094467163,
      "learning_rate": 2.64079655268759e-05,
      "loss": 0.7968,
      "step": 266
    },
    {
      "epoch": 0.30042194092827,
      "grad_norm": 0.25014856457710266,
      "learning_rate": 2.605362050924848e-05,
      "loss": 0.7739,
      "step": 267
    },
    {
      "epoch": 0.30154711673699014,
      "grad_norm": 0.2641415297985077,
      "learning_rate": 2.57008293378697e-05,
      "loss": 0.8149,
      "step": 268
    },
    {
      "epoch": 0.30267229254571026,
      "grad_norm": 0.25722652673721313,
      "learning_rate": 2.534961490485313e-05,
      "loss": 0.6831,
      "step": 269
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 0.2503587305545807,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6551,
      "step": 270
    },
    {
      "epoch": 0.3049226441631505,
      "grad_norm": 0.2686573266983032,
      "learning_rate": 2.4652007309320498e-05,
      "loss": 0.7863,
      "step": 271
    },
    {
      "epoch": 0.3060478199718706,
      "grad_norm": 0.27820244431495667,
      "learning_rate": 2.430565941356157e-05,
      "loss": 0.7644,
      "step": 272
    },
    {
      "epoch": 0.3071729957805907,
      "grad_norm": 0.27415186166763306,
      "learning_rate": 2.3960978786741877e-05,
      "loss": 0.756,
      "step": 273
    },
    {
      "epoch": 0.30829817158931083,
      "grad_norm": 0.28485107421875,
      "learning_rate": 2.361798779469336e-05,
      "loss": 0.7773,
      "step": 274
    },
    {
      "epoch": 0.30942334739803096,
      "grad_norm": 0.2954002022743225,
      "learning_rate": 2.3276708693609943e-05,
      "loss": 0.7728,
      "step": 275
    },
    {
      "epoch": 0.3105485232067511,
      "grad_norm": 0.2666501998901367,
      "learning_rate": 2.2937163628603435e-05,
      "loss": 0.6268,
      "step": 276
    },
    {
      "epoch": 0.31167369901547115,
      "grad_norm": 0.27716466784477234,
      "learning_rate": 2.259937463226651e-05,
      "loss": 0.6935,
      "step": 277
    },
    {
      "epoch": 0.3127988748241913,
      "grad_norm": 0.2816527485847473,
      "learning_rate": 2.2263363623243054e-05,
      "loss": 0.7137,
      "step": 278
    },
    {
      "epoch": 0.3139240506329114,
      "grad_norm": 0.29209843277931213,
      "learning_rate": 2.192915240480596e-05,
      "loss": 0.7184,
      "step": 279
    },
    {
      "epoch": 0.3150492264416315,
      "grad_norm": 0.3039759397506714,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 0.8377,
      "step": 280
    },
    {
      "epoch": 0.3161744022503516,
      "grad_norm": 0.29953083395957947,
      "learning_rate": 2.1266215967445824e-05,
      "loss": 0.7513,
      "step": 281
    },
    {
      "epoch": 0.3172995780590717,
      "grad_norm": 0.29667040705680847,
      "learning_rate": 2.0937533765518187e-05,
      "loss": 0.7013,
      "step": 282
    },
    {
      "epoch": 0.31842475386779184,
      "grad_norm": 0.30537861585617065,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6985,
      "step": 283
    },
    {
      "epoch": 0.31954992967651197,
      "grad_norm": 0.2818076014518738,
      "learning_rate": 2.0285848032369137e-05,
      "loss": 0.5899,
      "step": 284
    },
    {
      "epoch": 0.3206751054852321,
      "grad_norm": 0.3025727868080139,
      "learning_rate": 1.996288678810105e-05,
      "loss": 0.6654,
      "step": 285
    },
    {
      "epoch": 0.32180028129395216,
      "grad_norm": 0.2751609683036804,
      "learning_rate": 1.9641874609064443e-05,
      "loss": 0.5649,
      "step": 286
    },
    {
      "epoch": 0.3229254571026723,
      "grad_norm": 0.29040881991386414,
      "learning_rate": 1.932283232527956e-05,
      "loss": 0.5611,
      "step": 287
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 0.2740771770477295,
      "learning_rate": 1.9005780638942982e-05,
      "loss": 0.4361,
      "step": 288
    },
    {
      "epoch": 0.32517580872011254,
      "grad_norm": 0.2771192789077759,
      "learning_rate": 1.8690740123084316e-05,
      "loss": 0.4164,
      "step": 289
    },
    {
      "epoch": 0.3263009845288326,
      "grad_norm": 0.305276483297348,
      "learning_rate": 1.837773122023114e-05,
      "loss": 0.5081,
      "step": 290
    },
    {
      "epoch": 0.32742616033755273,
      "grad_norm": 0.31528910994529724,
      "learning_rate": 1.8066774241082612e-05,
      "loss": 0.5404,
      "step": 291
    },
    {
      "epoch": 0.32855133614627285,
      "grad_norm": 0.34744343161582947,
      "learning_rate": 1.7757889363191483e-05,
      "loss": 0.587,
      "step": 292
    },
    {
      "epoch": 0.329676511954993,
      "grad_norm": 0.31660598516464233,
      "learning_rate": 1.745109662965481e-05,
      "loss": 0.389,
      "step": 293
    },
    {
      "epoch": 0.3308016877637131,
      "grad_norm": 0.3436177968978882,
      "learning_rate": 1.714641594781347e-05,
      "loss": 0.417,
      "step": 294
    },
    {
      "epoch": 0.3319268635724332,
      "grad_norm": 0.3294260799884796,
      "learning_rate": 1.684386708796025e-05,
      "loss": 0.3738,
      "step": 295
    },
    {
      "epoch": 0.3330520393811533,
      "grad_norm": 0.35129880905151367,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.3655,
      "step": 296
    },
    {
      "epoch": 0.3341772151898734,
      "grad_norm": 0.4063621759414673,
      "learning_rate": 1.62452432224612e-05,
      "loss": 0.4208,
      "step": 297
    },
    {
      "epoch": 0.33530239099859355,
      "grad_norm": 0.4242677092552185,
      "learning_rate": 1.5949207060660138e-05,
      "loss": 0.4233,
      "step": 298
    },
    {
      "epoch": 0.3364275668073136,
      "grad_norm": 0.43796253204345703,
      "learning_rate": 1.5655380406016235e-05,
      "loss": 0.3132,
      "step": 299
    },
    {
      "epoch": 0.33755274261603374,
      "grad_norm": 0.5782553553581238,
      "learning_rate": 1.536378232452003e-05,
      "loss": 0.4808,
      "step": 300
    },
    {
      "epoch": 0.33755274261603374,
      "eval_loss": 0.5779129862785339,
      "eval_runtime": 122.5982,
      "eval_samples_per_second": 12.211,
      "eval_steps_per_second": 3.059,
      "step": 300
    },
    {
      "epoch": 0.33867791842475387,
      "grad_norm": 0.201891228556633,
      "learning_rate": 1.5074431737553157e-05,
      "loss": 0.3725,
      "step": 301
    },
    {
      "epoch": 0.339803094233474,
      "grad_norm": 0.20395103096961975,
      "learning_rate": 1.4787347420660541e-05,
      "loss": 0.438,
      "step": 302
    },
    {
      "epoch": 0.3409282700421941,
      "grad_norm": 0.20372365415096283,
      "learning_rate": 1.4502548002332088e-05,
      "loss": 0.5009,
      "step": 303
    },
    {
      "epoch": 0.3420534458509142,
      "grad_norm": 0.20695868134498596,
      "learning_rate": 1.422005196279395e-05,
      "loss": 0.526,
      "step": 304
    },
    {
      "epoch": 0.3431786216596343,
      "grad_norm": 0.1962495595216751,
      "learning_rate": 1.3939877632809278e-05,
      "loss": 0.5019,
      "step": 305
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 0.21751022338867188,
      "learning_rate": 1.3662043192488849e-05,
      "loss": 0.5188,
      "step": 306
    },
    {
      "epoch": 0.34542897327707456,
      "grad_norm": 0.23039577901363373,
      "learning_rate": 1.338656667011134e-05,
      "loss": 0.6243,
      "step": 307
    },
    {
      "epoch": 0.3465541490857947,
      "grad_norm": 0.2354414016008377,
      "learning_rate": 1.3113465940953495e-05,
      "loss": 0.721,
      "step": 308
    },
    {
      "epoch": 0.34767932489451475,
      "grad_norm": 0.2358129769563675,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.654,
      "step": 309
    },
    {
      "epoch": 0.3488045007032349,
      "grad_norm": 0.22713761031627655,
      "learning_rate": 1.257446259144494e-05,
      "loss": 0.602,
      "step": 310
    },
    {
      "epoch": 0.349929676511955,
      "grad_norm": 0.24341897666454315,
      "learning_rate": 1.2308594946249163e-05,
      "loss": 0.7296,
      "step": 311
    },
    {
      "epoch": 0.3510548523206751,
      "grad_norm": 0.24240520596504211,
      "learning_rate": 1.204517304231343e-05,
      "loss": 0.7068,
      "step": 312
    },
    {
      "epoch": 0.3521800281293952,
      "grad_norm": 0.25806447863578796,
      "learning_rate": 1.178421397270758e-05,
      "loss": 0.8166,
      "step": 313
    },
    {
      "epoch": 0.3533052039381153,
      "grad_norm": 0.2570001780986786,
      "learning_rate": 1.1525734670691701e-05,
      "loss": 0.7651,
      "step": 314
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 0.2566550076007843,
      "learning_rate": 1.1269751908617277e-05,
      "loss": 0.7221,
      "step": 315
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.2717800736427307,
      "learning_rate": 1.1016282296838887e-05,
      "loss": 0.8671,
      "step": 316
    },
    {
      "epoch": 0.3566807313642757,
      "grad_norm": 0.276123046875,
      "learning_rate": 1.0765342282636416e-05,
      "loss": 0.8627,
      "step": 317
    },
    {
      "epoch": 0.35780590717299576,
      "grad_norm": 0.26286810636520386,
      "learning_rate": 1.0516948149147754e-05,
      "loss": 0.7519,
      "step": 318
    },
    {
      "epoch": 0.3589310829817159,
      "grad_norm": 0.27873629331588745,
      "learning_rate": 1.0271116014312293e-05,
      "loss": 0.811,
      "step": 319
    },
    {
      "epoch": 0.360056258790436,
      "grad_norm": 0.27732256054878235,
      "learning_rate": 1.0027861829824952e-05,
      "loss": 0.747,
      "step": 320
    },
    {
      "epoch": 0.36118143459915614,
      "grad_norm": 0.271786630153656,
      "learning_rate": 9.787201380101157e-06,
      "loss": 0.7525,
      "step": 321
    },
    {
      "epoch": 0.3623066104078762,
      "grad_norm": 0.28306639194488525,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8081,
      "step": 322
    },
    {
      "epoch": 0.36343178621659633,
      "grad_norm": 0.288723349571228,
      "learning_rate": 9.313723980074018e-06,
      "loss": 0.8391,
      "step": 323
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 0.2829471528530121,
      "learning_rate": 9.080937753040646e-06,
      "loss": 0.8146,
      "step": 324
    },
    {
      "epoch": 0.3656821378340366,
      "grad_norm": 0.2665492594242096,
      "learning_rate": 8.850806705317183e-06,
      "loss": 0.6112,
      "step": 325
    },
    {
      "epoch": 0.3668073136427567,
      "grad_norm": 0.2935864329338074,
      "learning_rate": 8.623345769777514e-06,
      "loss": 0.8316,
      "step": 326
    },
    {
      "epoch": 0.3679324894514768,
      "grad_norm": 0.2984178066253662,
      "learning_rate": 8.398569706035792e-06,
      "loss": 0.789,
      "step": 327
    },
    {
      "epoch": 0.3690576652601969,
      "grad_norm": 0.2921222746372223,
      "learning_rate": 8.176493099488663e-06,
      "loss": 0.7701,
      "step": 328
    },
    {
      "epoch": 0.370182841068917,
      "grad_norm": 0.2875445485115051,
      "learning_rate": 7.957130360368898e-06,
      "loss": 0.708,
      "step": 329
    },
    {
      "epoch": 0.37130801687763715,
      "grad_norm": 0.2886877954006195,
      "learning_rate": 7.740495722810271e-06,
      "loss": 0.5826,
      "step": 330
    },
    {
      "epoch": 0.3724331926863572,
      "grad_norm": 0.29971715807914734,
      "learning_rate": 7.526603243923957e-06,
      "loss": 0.6209,
      "step": 331
    },
    {
      "epoch": 0.37355836849507734,
      "grad_norm": 0.28758934140205383,
      "learning_rate": 7.315466802886401e-06,
      "loss": 0.5842,
      "step": 332
    },
    {
      "epoch": 0.37468354430379747,
      "grad_norm": 0.29430586099624634,
      "learning_rate": 7.107100100038671e-06,
      "loss": 0.5808,
      "step": 333
    },
    {
      "epoch": 0.3758087201125176,
      "grad_norm": 0.29550546407699585,
      "learning_rate": 6.901516655997536e-06,
      "loss": 0.6218,
      "step": 334
    },
    {
      "epoch": 0.3769338959212377,
      "grad_norm": 0.30380144715309143,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.5913,
      "step": 335
    },
    {
      "epoch": 0.3780590717299578,
      "grad_norm": 0.3008062541484833,
      "learning_rate": 6.498752722928042e-06,
      "loss": 0.5062,
      "step": 336
    },
    {
      "epoch": 0.3791842475386779,
      "grad_norm": 0.3103947639465332,
      "learning_rate": 6.301598368674105e-06,
      "loss": 0.5587,
      "step": 337
    },
    {
      "epoch": 0.38030942334739803,
      "grad_norm": 0.310254842042923,
      "learning_rate": 6.107279541079769e-06,
      "loss": 0.5346,
      "step": 338
    },
    {
      "epoch": 0.38143459915611816,
      "grad_norm": 0.3149080276489258,
      "learning_rate": 5.915808849215304e-06,
      "loss": 0.4796,
      "step": 339
    },
    {
      "epoch": 0.38255977496483823,
      "grad_norm": 0.2941981852054596,
      "learning_rate": 5.727198717339511e-06,
      "loss": 0.3937,
      "step": 340
    },
    {
      "epoch": 0.38368495077355835,
      "grad_norm": 0.31065768003463745,
      "learning_rate": 5.54146138409355e-06,
      "loss": 0.3904,
      "step": 341
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 0.30580249428749084,
      "learning_rate": 5.358608901706802e-06,
      "loss": 0.3202,
      "step": 342
    },
    {
      "epoch": 0.3859353023909986,
      "grad_norm": 0.3562416136264801,
      "learning_rate": 5.178653135214812e-06,
      "loss": 0.4241,
      "step": 343
    },
    {
      "epoch": 0.3870604781997187,
      "grad_norm": 0.30645987391471863,
      "learning_rate": 5.001605761689398e-06,
      "loss": 0.3141,
      "step": 344
    },
    {
      "epoch": 0.3881856540084388,
      "grad_norm": 0.38345733284950256,
      "learning_rate": 4.827478269480895e-06,
      "loss": 0.49,
      "step": 345
    },
    {
      "epoch": 0.3893108298171589,
      "grad_norm": 0.3593797981739044,
      "learning_rate": 4.65628195747273e-06,
      "loss": 0.3769,
      "step": 346
    },
    {
      "epoch": 0.39043600562587905,
      "grad_norm": 0.4052690267562866,
      "learning_rate": 4.488027934348271e-06,
      "loss": 0.4271,
      "step": 347
    },
    {
      "epoch": 0.39156118143459917,
      "grad_norm": 0.4411349892616272,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.4206,
      "step": 348
    },
    {
      "epoch": 0.3926863572433193,
      "grad_norm": 0.4520365595817566,
      "learning_rate": 4.16039023417088e-06,
      "loss": 0.4025,
      "step": 349
    },
    {
      "epoch": 0.39381153305203936,
      "grad_norm": 0.6150334477424622,
      "learning_rate": 4.001027817058789e-06,
      "loss": 0.4425,
      "step": 350
    },
    {
      "epoch": 0.39381153305203936,
      "eval_loss": 0.5738900899887085,
      "eval_runtime": 123.3985,
      "eval_samples_per_second": 12.131,
      "eval_steps_per_second": 3.039,
      "step": 350
    },
    {
      "epoch": 0.3949367088607595,
      "grad_norm": 0.18382947146892548,
      "learning_rate": 3.844650207332562e-06,
      "loss": 0.372,
      "step": 351
    },
    {
      "epoch": 0.3960618846694796,
      "grad_norm": 0.18228398263454437,
      "learning_rate": 3.691267552111183e-06,
      "loss": 0.3865,
      "step": 352
    },
    {
      "epoch": 0.39718706047819974,
      "grad_norm": 0.19391196966171265,
      "learning_rate": 3.54088980417534e-06,
      "loss": 0.518,
      "step": 353
    },
    {
      "epoch": 0.3983122362869198,
      "grad_norm": 0.20379137992858887,
      "learning_rate": 3.393526721321616e-06,
      "loss": 0.6073,
      "step": 354
    },
    {
      "epoch": 0.39943741209563993,
      "grad_norm": 0.20377278327941895,
      "learning_rate": 3.249187865729264e-06,
      "loss": 0.5355,
      "step": 355
    },
    {
      "epoch": 0.40056258790436006,
      "grad_norm": 0.21739913523197174,
      "learning_rate": 3.1078826033397843e-06,
      "loss": 0.5892,
      "step": 356
    },
    {
      "epoch": 0.4016877637130802,
      "grad_norm": 0.20590797066688538,
      "learning_rate": 2.9696201032491434e-06,
      "loss": 0.5308,
      "step": 357
    },
    {
      "epoch": 0.4028129395218003,
      "grad_norm": 0.22945421934127808,
      "learning_rate": 2.8344093371128424e-06,
      "loss": 0.612,
      "step": 358
    },
    {
      "epoch": 0.4039381153305204,
      "grad_norm": 0.23170845210552216,
      "learning_rate": 2.70225907856374e-06,
      "loss": 0.6246,
      "step": 359
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 0.23253555595874786,
      "learning_rate": 2.573177902642726e-06,
      "loss": 0.6423,
      "step": 360
    },
    {
      "epoch": 0.4061884669479606,
      "grad_norm": 0.23829902708530426,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6802,
      "step": 361
    },
    {
      "epoch": 0.40731364275668075,
      "grad_norm": 0.24621927738189697,
      "learning_rate": 2.324256102563188e-06,
      "loss": 0.6475,
      "step": 362
    },
    {
      "epoch": 0.4084388185654008,
      "grad_norm": 0.24897930026054382,
      "learning_rate": 2.204431630583548e-06,
      "loss": 0.7314,
      "step": 363
    },
    {
      "epoch": 0.40956399437412094,
      "grad_norm": 0.25607559084892273,
      "learning_rate": 2.087708544541689e-06,
      "loss": 0.7108,
      "step": 364
    },
    {
      "epoch": 0.41068917018284107,
      "grad_norm": 0.26042604446411133,
      "learning_rate": 1.974094418431388e-06,
      "loss": 0.8427,
      "step": 365
    },
    {
      "epoch": 0.4118143459915612,
      "grad_norm": 0.2578832805156708,
      "learning_rate": 1.8635966245104664e-06,
      "loss": 0.7355,
      "step": 366
    },
    {
      "epoch": 0.4129395218002813,
      "grad_norm": 0.25586313009262085,
      "learning_rate": 1.7562223328224325e-06,
      "loss": 0.7442,
      "step": 367
    },
    {
      "epoch": 0.4140646976090014,
      "grad_norm": 0.2767845094203949,
      "learning_rate": 1.6519785107311891e-06,
      "loss": 0.8506,
      "step": 368
    },
    {
      "epoch": 0.4151898734177215,
      "grad_norm": 0.2640194892883301,
      "learning_rate": 1.5508719224689717e-06,
      "loss": 0.7084,
      "step": 369
    },
    {
      "epoch": 0.41631504922644164,
      "grad_norm": 0.2685393989086151,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 0.7258,
      "step": 370
    },
    {
      "epoch": 0.41744022503516176,
      "grad_norm": 0.2706719636917114,
      "learning_rate": 1.358096486081778e-06,
      "loss": 0.7101,
      "step": 371
    },
    {
      "epoch": 0.41856540084388183,
      "grad_norm": 0.27270835638046265,
      "learning_rate": 1.2664401468786114e-06,
      "loss": 0.7251,
      "step": 372
    },
    {
      "epoch": 0.41969057665260195,
      "grad_norm": 0.28525063395500183,
      "learning_rate": 1.1779460585363944e-06,
      "loss": 0.7922,
      "step": 373
    },
    {
      "epoch": 0.4208157524613221,
      "grad_norm": 0.2806113362312317,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7772,
      "step": 374
    },
    {
      "epoch": 0.4219409282700422,
      "grad_norm": 0.29236048460006714,
      "learning_rate": 1.0104673978866164e-06,
      "loss": 0.776,
      "step": 375
    },
    {
      "epoch": 0.42306610407876233,
      "grad_norm": 0.2895606756210327,
      "learning_rate": 9.314936930293283e-07,
      "loss": 0.7037,
      "step": 376
    },
    {
      "epoch": 0.4241912798874824,
      "grad_norm": 0.2893851101398468,
      "learning_rate": 8.557039732283944e-07,
      "loss": 0.7635,
      "step": 377
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 0.2851521670818329,
      "learning_rate": 7.83103156370113e-07,
      "loss": 0.6912,
      "step": 378
    },
    {
      "epoch": 0.42644163150492265,
      "grad_norm": 0.2914351224899292,
      "learning_rate": 7.136959534174592e-07,
      "loss": 0.6818,
      "step": 379
    },
    {
      "epoch": 0.42756680731364277,
      "grad_norm": 0.2961958348751068,
      "learning_rate": 6.474868681043578e-07,
      "loss": 0.6924,
      "step": 380
    },
    {
      "epoch": 0.4286919831223629,
      "grad_norm": 0.30675557255744934,
      "learning_rate": 5.844801966434832e-07,
      "loss": 0.768,
      "step": 381
    },
    {
      "epoch": 0.42981715893108297,
      "grad_norm": 0.303774356842041,
      "learning_rate": 5.246800274474439e-07,
      "loss": 0.6428,
      "step": 382
    },
    {
      "epoch": 0.4309423347398031,
      "grad_norm": 0.3004835844039917,
      "learning_rate": 4.680902408635335e-07,
      "loss": 0.6931,
      "step": 383
    },
    {
      "epoch": 0.4320675105485232,
      "grad_norm": 0.29980704188346863,
      "learning_rate": 4.1471450892189846e-07,
      "loss": 0.5863,
      "step": 384
    },
    {
      "epoch": 0.43319268635724334,
      "grad_norm": 0.29202115535736084,
      "learning_rate": 3.6455629509730136e-07,
      "loss": 0.5396,
      "step": 385
    },
    {
      "epoch": 0.4343178621659634,
      "grad_norm": 0.3045811653137207,
      "learning_rate": 3.1761885408435054e-07,
      "loss": 0.5696,
      "step": 386
    },
    {
      "epoch": 0.43544303797468353,
      "grad_norm": 0.29848921298980713,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.4808,
      "step": 387
    },
    {
      "epoch": 0.43656821378340366,
      "grad_norm": 0.29339462518692017,
      "learning_rate": 2.334182641175686e-07,
      "loss": 0.4606,
      "step": 388
    },
    {
      "epoch": 0.4376933895921238,
      "grad_norm": 0.31360113620758057,
      "learning_rate": 1.9616057881935436e-07,
      "loss": 0.4696,
      "step": 389
    },
    {
      "epoch": 0.4388185654008439,
      "grad_norm": 0.31095123291015625,
      "learning_rate": 1.6213459328950352e-07,
      "loss": 0.4802,
      "step": 390
    },
    {
      "epoch": 0.439943741209564,
      "grad_norm": 0.30314531922340393,
      "learning_rate": 1.3134251542544774e-07,
      "loss": 0.4323,
      "step": 391
    },
    {
      "epoch": 0.4410689170182841,
      "grad_norm": 0.34104612469673157,
      "learning_rate": 1.0378634328099269e-07,
      "loss": 0.4987,
      "step": 392
    },
    {
      "epoch": 0.4421940928270042,
      "grad_norm": 0.3525398075580597,
      "learning_rate": 7.946786493666647e-08,
      "loss": 0.4656,
      "step": 393
    },
    {
      "epoch": 0.44331926863572435,
      "grad_norm": 0.32821884751319885,
      "learning_rate": 5.838865838366792e-08,
      "loss": 0.3665,
      "step": 394
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.3422605097293854,
      "learning_rate": 4.055009142152067e-08,
      "loss": 0.3255,
      "step": 395
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 0.3505786061286926,
      "learning_rate": 2.595332156925534e-08,
      "loss": 0.3839,
      "step": 396
    },
    {
      "epoch": 0.44669479606188467,
      "grad_norm": 0.35224196314811707,
      "learning_rate": 1.4599295990352924e-08,
      "loss": 0.3063,
      "step": 397
    },
    {
      "epoch": 0.4478199718706048,
      "grad_norm": 0.39496955275535583,
      "learning_rate": 6.488751431266149e-09,
      "loss": 0.3376,
      "step": 398
    },
    {
      "epoch": 0.4489451476793249,
      "grad_norm": 0.4384694993495941,
      "learning_rate": 1.622214173602199e-09,
      "loss": 0.3727,
      "step": 399
    },
    {
      "epoch": 0.450070323488045,
      "grad_norm": 0.5900406837463379,
      "learning_rate": 0.0,
      "loss": 0.3785,
      "step": 400
    },
    {
      "epoch": 0.450070323488045,
      "eval_loss": 0.5731000304222107,
      "eval_runtime": 122.6526,
      "eval_samples_per_second": 12.205,
      "eval_steps_per_second": 3.057,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.392326289935565e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}